© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18011
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prega
    -0.08
    aldas
    -0.07
    æī¬éķ¿
    -0.06
    ,:
    -0.06
    bergen
    -0.06
    è½
    -0.06
    \<
    -0.06
    rown
    -0.06
    é«ĺåĵģè´¨çļĦ
    -0.06
    ([^
    -0.06
    POSITIVE LOGITS
    reed
    0.08
    éĺ¿åį¡
    0.08
    æħ§èģª
    0.08
    åĭ¤åĭ¤æģ³æģ³
    0.07
    CoV
    0.07
    oden
    0.07
    赤水
    0.07
    äºī
    0.07
    ÑĢаÑĨиÑı
    0.07
    çķ¥
    0.07
    Activations Density 0.000%

    No Known Activations